Files
headroom/tests/test_thinking_compactor_version_gate.py
cc1eb5402a fix(thinking): leave a thinking block with a null or non-string value unchanged (#4562)
## Description

`compact_thinking_to_text` says it never raises
(`headroom/transforms/thinking_compactor.py:115`), but a block with
`"thinking": null` reached `text.split()` and raised `AttributeError`. A
non-string `thinking` value now leaves the block as it is, like the
`isinstance` guard `compact_reasoning_openai_chat` already has. Item 1
of #4546.

Refs #4546

## Type of Change

- [x] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Performance improvement
- [ ] Code refactoring (no functional changes)

## Changes Made

- `headroom/transforms/thinking_compactor.py`: `text =
block.get("thinking")`; if it is not a `str`, the block is appended
unchanged.
- `tests/test_thinking_compactor_version_gate.py`:
`test_compact_thinking_to_text_leaves_null_thinking_block_alone`.

## Testing

- [x] Unit tests pass (`pytest`)
- [x] Linting passes (`ruff check .`)
- [ ] Type checking passes (`mypy headroom`)
- [x] New tests added for new functionality
- [x] Manual testing performed

### Test Output

```text
# fail before (source at a2d4fe72, new test kept)
1 failed, 17 deselected

# pass after: tests/test_thinking_compactor_version_gate.py
18 passed

# ruff check / ruff format --check: All checks passed! / 2 files already formatted
```

## Real Behavior Proof

- Environment: Ubuntu (WSL2) on Windows 11, Python 3.12.15, `headroom`
Python source at `a2d4fe72` and at this branch, `_core` from the 0.42.0
wheel, offline.
- Exact command / steps: called `compact_thinking_to_text` on a
conversation whose older assistant turn has `{"type": "thinking",
"thinking": None}` (the snippet in #4546).
- Observed result: on `a2d4fe72`: `AttributeError: 'NoneType' object has
no attribute 'split'`. On this branch: the call returns, and the null
block is left in place unchanged.
- Not tested: the full suite and `mypy`. I found no production caller of
`compact_thinking_to_text` under `headroom/` (the proxy imports only
`compact_reasoning_openai_chat`), so this affects SDK callers.

## Runtime Rollout Safety

- Rollout-managed feature(s): None.
- Minimum rollout channel: N/A
- Stable/default behavior changed: Only for an input that previously
raised.
- Kill switch / disable path: None needed; revert.
- Unsafe override required: No
- Qualification impact: None expected
- Rollback path: revert this commit.

## Review Readiness

- [x] I have performed a self-review
- [x] This PR is ready for human review

## Checklist

- [x] My code follows the project's style guidelines
- [x] I have performed a self-review of my code
- [x] I have commented my code, particularly in hard-to-understand areas
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my
feature works
- [x] New and existing unit tests pass locally with my changes
- [x] I did **not** edit `CHANGELOG.md` — it is generated by
release-please from my Conventional Commit PR title (a CI guard enforces
this)

## Screenshots (if applicable)

N/A

## Additional Notes

Split out of #4560 (one logical change per PR, as CONTRIBUTING asks).
The three items of #4546 are now #4560 (update check), #4562 (null
thinking block) and #4563 (interior blank CSV rows).

Produced with AI assistance (Claude Code) operated by me (HetCreep); the
reproduction was run on my machine against a clone of the repository.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: JD Davis <mxjerrett@gmail.com>
2026-11-04 23:10:00 -06:00

74 lines
3.0 KiB
Python

"""Version-gate tests for thinking_compactor.bills_prior_thinking.
The gate decides whether a model re-bills prior-turn thinking (so compaction
pays) or strips it server-side (so compacting would turn free thinking into
billed text). It parses the version out of the model id, and must not mistake
the ``YYYYMMDD`` release-date suffix for the minor version.
"""
from __future__ import annotations
import pytest
from headroom.transforms.thinking_compactor import bills_prior_thinking
@pytest.mark.parametrize(
("model", "expected"),
[
# Major-only ids with a date suffix: the date must NOT be read as the
# minor version. Claude 4.0 strips prior thinking server-side -> False.
("claude-sonnet-4-20250514", False),
("claude-opus-4-20250514", False),
("claude-opus-4", False),
# Explicit minor below the 4.6 threshold -> strips -> False.
("claude-sonnet-4-5-20250929", False),
("claude-haiku-4-5-20251001", False),
("claude-opus-4-1-20250805", False),
("claude-opus-4-5-20250101", False),
# 4.6+ and the 5 family re-bill prior thinking -> True.
("claude-opus-4-6", True),
("claude-sonnet-4-6", True),
("claude-opus-4-8", True),
("claude-sonnet-5", True),
("claude-sonnet-5-20260101", True),
("claude-haiku-5-5", True),
# Legacy 3.x naming (with date) stays below threshold.
("claude-3-5-sonnet-20241022", False),
("claude-3-opus-20240229", False),
# No version at all -> conservative False.
("some-unversioned-model", False),
],
)
def test_bills_prior_thinking_version_gate(model: str, expected: bool) -> None:
assert bills_prior_thinking(model) is expected
def test_date_suffix_is_not_read_as_minor_version() -> None:
"""Regression for the specific inversion: a major-only id whose 8-digit date
suffix was parsed as the minor version, flipping a strip-model to 'bills'."""
# Same major (4), only the date suffix differs from an explicit-minor id.
assert bills_prior_thinking("claude-sonnet-4-20250514") is False
# Sanity: the real 4.6 id still bills.
assert bills_prior_thinking("claude-sonnet-4-6-20260101") is True
def test_compact_thinking_to_text_leaves_null_thinking_block_alone() -> None:
"""``"thinking": null`` must not raise (docstring: "Never raises")."""
from headroom.transforms.thinking_compactor import compact_thinking_to_text
class _K:
def compress(self, text, **kwargs):
return type("R", (), {"compressed": text[:10]})()
null_block = {"type": "thinking", "thinking": None, "signature": "s"}
msgs = [
{"role": "user", "content": "q"},
{"role": "assistant", "content": [null_block, {"type": "text", "text": "a"}]},
{"role": "user", "content": "q2"},
{"role": "assistant", "content": [{"type": "text", "text": "b"}]},
]
out, stats = compact_thinking_to_text(msgs, kompress=_K())
assert out[1]["content"][0] == null_block
assert stats["blocks"] == 0